UltraPose: Synthesizing Dense Pose with 1 Billion Points by Human-body Decoupling 3D Model

MomoAILab

Last update: Dec 21, 2022

Related tags

Deep Learning ultrapose

Overview

UltraPose: Synthesizing Dense Pose with 1 Billion Points by Human-body Decoupling 3D Model

Official repository for the ICCV 2021 paper:
UltraPose: Synthesizing Dense Pose with 1 Billion Points by Human-body Decoupling 3D Model [PDF]

Haonan Yan, Jiaqi Chen, Xujie Zhang, Shengkai Zhang, Nianhong Jiao, Xiaodan Liang, Tianxiang Zheng

Introduction

In this work, we introduce a new 3D human-body model with a series of decoupled parameters that could freely control the generation of the body. Furthermore, we build a data generation system based on this decoupling 3D model, and construct an ultra dense synthetic benchmark UltraPose, containing around 1.3 billion corresponding points.

Code and Dataset

will be coming soon.

Citation

If you use this code and benchmark for your research, please cite our work:

@inproceedings{yan2021ultrapose,
  title={UltraPose: Synthesizing Dense Pose With 1 Billion Points by Human-Body Decoupling 3D Model},
  author={Yan, Haonan and Chen, Jiaqi and Zhang, Xujie and Zhang, Shengkai and Jiao, Nianhong and Liang, Xiaodan and Zheng, Tianxiang},
  booktitle={Proceedings of the IEEE/CVF International Conference on Computer Vision},
  pages={10891--10900},
  year={2021}
}

You might also like...

Ultra-lightweight human body posture key point CNN model. ModelSize:2.3MB HUAWEI P40 NCNN benchmark: 6ms/img,

Ultralight-SimplePose Support NCNN mobile terminal deployment Based on MXNET(=1.5.1) GLUON(=0.7.0) framework Top-down strategy: The input image is t

223 Dec 27, 2022

SMPL-X: A new joint 3D model of the human body, face and hands together

SMPL-X: A new joint 3D model of the human body, face and hands together [Paper Page] [Paper] [Supp. Mat.] Table of Contents License Description News I

1k Jan 9, 2023

《Unsupervised 3D Human Pose Representation with Viewpoint and Pose Disentanglement》(ECCV 2020) GitHub: [fig9]

Unsupervised 3D Human Pose Representation [Paper] The implementation of our paper Unsupervised 3D Human Pose Representation with Viewpoint and Pose Di

42 Nov 24, 2022

Repository for the paper "PoseAug: A Differentiable Pose Augmentation Framework for 3D Human Pose Estimation", CVPR 2021.

PoseAug: A Differentiable Pose Augmentation Framework for 3D Human Pose Estimation Code repository for the paper: PoseAug: A Differentiable Pose Augme

328 Dec 17, 2022

FrankMocap: A Strong and Easy-to-use Single View 3D Hand+Body Pose Estimator

FrankMocap pursues an easy-to-use single view 3D motion capture system developed by Facebook AI Research (FAIR). FrankMocap provides state-of-the-art 3D pose estimation outputs for body, hand, and body+hands in a single system. The core objective of FrankMocap is to democratize the 3D human pose estimation technology, enabling anyone (researchers, engineers, developers, artists, and others) can easily obtain 3D motion capture outputs from videos and images.

1.9k Jan 7, 2023

Demo for Real-time RGBD-based Extended Body Pose Estimation paper

Real-time RGBD-based Extended Body Pose Estimation This repository is a real-time demo for our paper that was published at WACV 2021 conference The ou

118 Dec 26, 2022

Pose Detection and Machine Learning for real-time body posture analysis during exercise to provide audiovisual feedback on improvement of form.

Posture: Pose Tracking and Machine Learning for prescribing corrective suggestions to improve posture and form while exercising. This repository conta

10 Nov 11, 2022

pytorch implementation of openpose including Hand and Body Pose Estimation.

pytorch-openpose pytorch implementation of openpose including Body and Hand Pose Estimation, and the pytorch model is directly converted from openpose

1.4k Jan 7, 2023

[CVPR 2022 Oral] EPro-PnP: Generalized End-to-End Probabilistic Perspective-n-Points for Monocular Object Pose Estimation

EPro-PnP EPro-PnP: Generalized End-to-End Probabilistic Perspective-n-Points for Monocular Object Pose Estimation In CVPR 2022 (Oral). [paper] Hanshen

同济大学智能汽车研究所综合感知研究组 ( Comprehensive Perception Research Group under Institute of Intelligent Vehicles, School of Automotive Studies, Tongji University)

842 Jan 4, 2023

Comments

how to visualize the mesh model?

Hi , thanks for sharing this wonderful work, I have use the gen_iuv you provided to visualize the 2d points in original image like below , but it seem there are no vertex that can used for visualize the mesh model, can you provide? thanks~

opened by visonpon 1
关于code

Can you release a video of the demonstration? In addition, I want to know whether the parametric model it obtains is the size of the real scale? Because the size needs to be calculated, it is better if it is a real size. Can I use depth data or point cloud data to generate a parametric model?

opened by socketing 0
annotations

Thans for your excellent work! According to the paper, the pose data were rendered according to the 3d model, and there is no error. However, when I visual the test image,I found that there were obvious errors。so I want to know what went wrong? "Third, the generated data annotations are absolute truth values without any error, and perfectly repre- sent the corresponding relationship between the 2D image and the surface of human body."

opened by liuzhihui2046 2

UltraPose: Synthesizing Dense Pose with 1 Billion Points by Human-body Decoupling 3D Model

Related tags

Overview

UltraPose: Synthesizing Dense Pose with 1 Billion Points by Human-body Decoupling 3D Model

Introduction

Code and Dataset

Citation

You might also like...

Ultra-lightweight human body posture key point CNN model. ModelSize:2.3MB HUAWEI P40 NCNN benchmark: 6ms/img,

SMPL-X: A new joint 3D model of the human body, face and hands together

《Unsupervised 3D Human Pose Representation with Viewpoint and Pose Disentanglement》(ECCV 2020) GitHub: [fig9]

Repository for the paper "PoseAug: A Differentiable Pose Augmentation Framework for 3D Human Pose Estimation", CVPR 2021.

FrankMocap: A Strong and Easy-to-use Single View 3D Hand+Body Pose Estimator

Demo for Real-time RGBD-based Extended Body Pose Estimation paper

Pose Detection and Machine Learning for real-time body posture analysis during exercise to provide audiovisual feedback on improvement of form.

pytorch implementation of openpose including Hand and Body Pose Estimation.

[CVPR 2022 Oral] EPro-PnP: Generalized End-to-End Probabilistic Perspective-n-Points for Monocular Object Pose Estimation

Comments

how to visualize the mesh model?

关于code

annotations

Owner

MomoAILab

A Planar RGB-D SLAM which utilizes Manhattan World structure to provide optimal camera pose trajectory while also providing a sparse reconstruction containing points, lines and planes, and a dense surfel-based reconstruction.

HPRNet: Hierarchical Point Regression for Whole-Body Human Pose Estimation

Face and Pose detector that emits MQTT events when a face or human body is detected and not detected.

Synthesizing Long-Term 3D Human Motion and Interaction in 3D in CVPR2021

Expressive Body Capture: 3D Hands, Face, and Body from a Single Image

Full body anonymization - Realistic Full-Body Anonymization with Surface-Guided GANs

WormMovementSimulation - 3D Simulation of Worm Body Movement with Neurons attached to its body

[ICLR 2022] Contact Points Discovery for Soft-Body Manipulations with Differentiable Physics

PyTorch Language Model for 1-Billion Word (LM1B / GBW) Dataset

SE3 Pose Interp - Interpolate camera pose or trajectory in SE3, pose interpolation, trajectory interpolation